In statistics and machine learning, classification is the process of putting elements into existing sets that are called categories. In machine learning, classification is considered a supervised learning technique, which is where a set that is considered to contain correctly identified observations is used for training before working with the actual data.
A very popular and easy-to-implement classification method is called k-nearest neighbors (k-NN). The idea behind k-NN is that we can classify data items based on their similarity with other items. The k in k-NN denotes the number of neighbors that are going to be included in the decision, which means that k is a positive integer that is usually pretty small.
The input of the algorithm consists of the k-closest training examples in the feature space. An object is classified by a plurality vote of its neighbors,...